Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5764 Discussions

Modifyting the intermediate layer activations

Biswas__Sudi
Beginner
120 Views

How can we modify the input activations of the intermediate layers? For example, if we want to use input activations as int4 instead of FP32 or int8, how can we do it.

0 Kudos
1 Reply
Gouveia__César
New Contributor I
120 Views

Hi Sudi,

I think there isn't a easy way to perform what you are looking for, since the openvino converter (model optimizer) only provides reduced precisions of FP16 (half floats). If you run the model optimizer with -h flag you will find:

--data_type {FP16,FP32,half,float}
                        Data type for all intermediate tensors and weights. If
                        original model is in FP32 and --data_type=FP16 is
                        specified, all model weights and biases are quantized
                        to FP16.

Hope it helps,

César.

Reply